InterKey: Cross-modal Intersection Keypoints for Global Localization on OpenStreetMap
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866912614679838720 |
|---|---|
| author | Tran, Nguyen Hoang Khoi Berrio, Julie Stephany Shan, Mao Worrall, Stewart |
| author_facet | Tran, Nguyen Hoang Khoi Berrio, Julie Stephany Shan, Mao Worrall, Stewart |
| contents | Reliable global localization is critical for autonomous vehicles, especially in environments where GNSS is degraded or unavailable, such as urban canyons and tunnels. Although high-definition (HD) maps provide accurate priors, the cost of data collection, map construction, and maintenance limits scalability. OpenStreetMap (OSM) offers a free and globally available alternative, but its coarse abstraction poses challenges for matching with sensor data. We propose InterKey, a cross-modal framework that leverages road intersections as distinctive landmarks for global localization. Our method constructs compact binary descriptors by jointly encoding road and building imprints from point clouds and OSM. To bridge modality gaps, we introduce discrepancy mitigation, orientation determination, and area-equalized sampling strategies, enabling robust cross-modal matching. Experiments on the KITTI dataset demonstrate that InterKey achieves state-of-the-art accuracy, outperforming recent baselines by a large margin. The framework generalizes to sensors that can produce dense structural point clouds, offering a scalable and cost-effective solution for robust vehicle localization. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_13857 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | InterKey: Cross-modal Intersection Keypoints for Global Localization on OpenStreetMap Tran, Nguyen Hoang Khoi Berrio, Julie Stephany Shan, Mao Worrall, Stewart Robotics Computer Vision and Pattern Recognition Reliable global localization is critical for autonomous vehicles, especially in environments where GNSS is degraded or unavailable, such as urban canyons and tunnels. Although high-definition (HD) maps provide accurate priors, the cost of data collection, map construction, and maintenance limits scalability. OpenStreetMap (OSM) offers a free and globally available alternative, but its coarse abstraction poses challenges for matching with sensor data. We propose InterKey, a cross-modal framework that leverages road intersections as distinctive landmarks for global localization. Our method constructs compact binary descriptors by jointly encoding road and building imprints from point clouds and OSM. To bridge modality gaps, we introduce discrepancy mitigation, orientation determination, and area-equalized sampling strategies, enabling robust cross-modal matching. Experiments on the KITTI dataset demonstrate that InterKey achieves state-of-the-art accuracy, outperforming recent baselines by a large margin. The framework generalizes to sensors that can produce dense structural point clouds, offering a scalable and cost-effective solution for robust vehicle localization. |
| title | InterKey: Cross-modal Intersection Keypoints for Global Localization on OpenStreetMap |
| topic | Robotics Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2509.13857 |